From 772cfb6c4ec7770759b4e0c8552b934fe9ff897d Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Tue, 14 Apr 2026 22:38:17 -0700
Subject: [PATCH] fix: stale agent timeout, uv venv detection, empty response
 after tools, compression model fallback (#9051, #8620, #9400) (#10093)

Four independent fixes:

1. Reset activity timestamp on cached agent reuse (#9051)
   When the gateway reuses a cached AIAgent for a new turn, the
   _last_activity_ts from the previous turn (possibly hours ago)
   carried over. The inactivity timeout handler immediately saw
   the agent as idle for hours and killed it.

   Fix: reset _last_activity_ts, _last_activity_desc, and
   _api_call_count when retrieving an agent from the cache.

2. Detect uv-managed virtual environments (#8620 sub-issue 1)
   The systemd unit generator fell back to sys.executable (uv's
   standalone Python) when running under 'uv run', because
   sys.prefix == sys.base_prefix. The generated ExecStart pointed
   to a Python binary without site-packages.

   Fix: check VIRTUAL_ENV env var before falling back to
   sys.executable. uv sets VIRTUAL_ENV even when sys.prefix
   doesn't reflect the venv.

3. Nudge model to continue after empty post-tool response (#9400)
   Weaker models sometimes return empty after tool calls. The agent
   silently abandoned the remaining work.

   Fix: append assistant('(empty)') + user nudge message and retry
   once. Resets after each successful tool round.

4. Compression model fallback on permanent errors (#8620 sub-issue 4)
   When the default summary model (gemini-3-flash) returns 503
   'model_not_found' on custom proxies, the compressor entered a
   600s cooldown, leaving context growing unbounded.

   Fix: detect permanent model-not-found errors (503, 404,
   'model_not_found', 'no available channel') and fall back to
   using the main model for compression instead of entering
   cooldown. One-time fallback with immediate retry.

Test plan: 40 compressor tests + 97 gateway/CLI tests + 9 venv tests pass
---
 agent/context_compressor.py | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/agent/context_compressor.py b/agent/context_compressor.py
index 74bbbd5d0c8..ac5db77625e 100644
--- a/agent/context_compressor.py
+++ b/agent/context_compressor.py
@@ -693,6 +693,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             # Store for iterative updates on next compaction
             self._previous_summary = summary
             self._summary_failure_cooldown_until = 0.0
+            self._summary_model_fallen_back = False
             return self._with_summary_prefix(summary)
         except RuntimeError:
             # No provider configured — long cooldown, unlikely to self-resolve
@@ -703,6 +704,34 @@ The user has requested that this compaction PRIORITISE preserving all informatio
                             _SUMMARY_FAILURE_COOLDOWN_SECONDS)
             return None
         except Exception as e:
+            # If the summary model is different from the main model and the
+            # error looks permanent (model not found, 503, 404), fall back to
+            # using the main model instead of entering cooldown that leaves
+            # context growing unbounded.  (#8620 sub-issue 4)
+            _status = getattr(e, "status_code", None) or getattr(getattr(e, "response", None), "status_code", None)
+            _err_str = str(e).lower()
+            _is_model_not_found = (
+                _status in (404, 503)
+                or "model_not_found" in _err_str
+                or "does not exist" in _err_str
+                or "no available channel" in _err_str
+            )
+            if (
+                _is_model_not_found
+                and self.summary_model
+                and self.summary_model != self.model
+                and not getattr(self, "_summary_model_fallen_back", False)
+            ):
+                self._summary_model_fallen_back = True
+                logging.warning(
+                    "Summary model '%s' not available (%s). "
+                    "Falling back to main model '%s' for compression.",
+                    self.summary_model, e, self.model,
+                )
+                self.summary_model = ""  # empty = use main model
+                self._summary_failure_cooldown_until = 0.0  # no cooldown
+                return self._generate_summary(messages, summary_budget)  # retry immediately
+
             # Transient errors (timeout, rate limit, network) — shorter cooldown
             _transient_cooldown = 60
             self._summary_failure_cooldown_until = time.monotonic() + _transient_cooldown